1 2<!DOCTYPE html> 3<html lang="en"> 4<head>
4<script>
vendor: 330 bytes, line 4
4(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o),m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)})(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); ga('create', '
4UA-3974203-1
vendor: 35 bytes, line 4
4', 'auto'); ga('send', 'pageview');
4</script>
4 5 <meta charset="UTF-8"> 6 <title>Heng Fan - Selected Publications</title> 7 <meta name="viewport" content="width=device-width, initial-scale=1.0"> 8 <link rel="stylesheet" type="text/css" href="./stylefiles/global.css"> 9 <link rel="stylesheet" type="text/css" href="./stylefiles/navigation.css"> 10 <link rel="stylesheet" type="text/css" href="./stylefiles/home.css"> 11 <link rel="shortcut icon" href="./personal/favicon.ico" /> 12 <style>a{ TEXT-DECORATION:none}a:hover{TEXT-DECORATION:underline }</style> 13</head> 14<body> 15 16<div class="navi central_body"> 17 <a class="navi" href="./index.html">Home</a> 18 <a class="navi navi_active" href="./publications.html">Selected Publications</a> 19 <a class="navi" href="./group.html">Group</a> 20 <a class="navi" href="./teaching.html">Teaching</a> 21 <a class="navi" href="./service.html">Professional Activities</a> 22 <!--<a class="navi" href="./student.html">Student Supervision</a>--> 23</div> 24 25<div class="navi_bar"></div> 26 27<div class="central_body"> 28 <!-- full journal papers --> 29 30 <font size="3">For full publication list, please go to my <a href="https://scholar.google.com/citations?user=MVQYJiMAAAAJ" target="https://scholar.google.com/citations?user=MVQYJiMAAAAJ"><font color="#2D61FF">Google Scholar profile</font></a>.</font> 31 <br> 32 (*equal contribution, †equal advising and co-last authors) 33 <!-- <HR> --> 34 35 <!-- <font size="4" color="#2D61FF"><b>Pre-prints</b></font> 36 <br> --> 37 38 <!-- <table border=0 cellpadding=4> --> 39 40 <!-- 41 42 <tr> 43 <td><img src="./publication/fgd.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 44 <td valign=top> 45 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 46 <font style="font-weight:bold">Flow-Guided Diffusion for Video Inpainting</font> 47 <br> 48 <font color="#000000" >B. Gu, Y. Yu, H. Fan, and L. Zhang</font> 49 <br> 50 <font>arXiv:2311.15368, 2023. </font> 51 <br> 52 <a href="https://arxiv.org/abs/2311.15368" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/NevSNev/FGDVI" target="_blank"><font color="#2D61FF">code</font></a> 53 <br> 54 </p> 55 </td> 56 </tr> 57 58 <tr> 59 <td><img src="./publication/dmt.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 60 <td valign=top> 61 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 62 <font style="font-weight:bold">Deficiency-Aware Masked Transformer for Video Inpainting</font> 63 <br> 64 <font color="#000000" >Y. Yu, H. Fan, and L. Zhang</font> 65 <br> 66 <font>arXiv:2307.08629, 2023. </font> 67 <br> 68 <a href="https://arxiv.org/abs/2307.08629" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/yeates/DMT" target="_blank"><font color="#2D61FF">code</font></a> 69 <br> 70 </p> 71 </td> 72 </tr> --> 73 74 75 76 <!-- </table> --> 77 <HR> 78 79 <font size="4" color="black"><b>2026 / in press</b></font> 80 <br> 81 82 <table border=0 cellpadding=4> 83 84 <tr> 85 <td><img src="./publication/TeSCo.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 86 <td valign=top> 87 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 88 <font style="font-weight:bold">Exploiting Textual Semantics for Robust Cross-View Object Correspondence</font> 89 <br> 90 <font color="#000000">B. Fan, Y. Feng, Y. Huang, and H. Fan</font> 91 <br> 92 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2026.</font> 93 <br> 94 <a href="#" target="_blank"><font color="#2D61FF">paper</font></a> <a href="#" target="_blank"><font color="#2D61FF">code</font></a> 95 <br> 96 </p> 97 </td> 98 </tr> 99 100 <tr> 101 <td><img src="./publication/VQS.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 102 <td valign=top> 103 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 104 <font style="font-weight:bold">Towards Visual Query Segmentation in the Wild</font> 105 <br> 106 <font color="#000000">B. Fan*, M. Li*, H. Zhang*, S. Dong, N. Mareedu, X. Liu, W. Shi, Y. Feng, Y. Huang, and H. Fan</font> 107 <br> 108 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2026.</font> 109 <br> 110 <a href="#" target="_blank"><font color="#2D61FF">paper</font></a> <a href="#" target="_blank"><font color="#2D61FF">code-data</font></a> 111 <br> 112 </p> 113 </td> 114 </tr> 115 116 <tr> 117 <td><img src="./publication/emnlpfindings26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 118 <td valign=top> 119 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 120 <font style="font-weight:bold">Poly-FEVER: A Multilingual Hallucination Detection Benchmark</font> 121 <br> 122 <font color="#000000">H. Zhang, S. Anjum, H. Fan, W. Zheng, Y. Huang, and Y. Feng</font> 123 <br> 124 <font>Findings of the Conference on Empirical Methods in Natural Language Processing (<b>EMNLP Findings</b>), 2026.</font> 125 <br> 126 <a href="https://arxiv.org/abs/2503.16541" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://huggingface.co/datasets/HanzhiZhang/Poly-FEVER" target="_blank"><font color="#2D61FF">data</font></a> 127 <br> 128 </p> 129 </td> 130 </tr> 131 132 <tr> 133 <td><img src="./publication/sigspatial26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 134 <td valign=top> 135 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 136 <font style="font-weight:bold">SymNetPro: LOS-Aware Directional Multi-Transmitter Localization from Sparse Radio Observations</font> 137 <br> 138 <font color="#000000">L. Ye, H. Fan, and Y. Huang</font> 139 <br> 140 <font>ACM International Conference on Advances in Geographic Information Systems (<b>SIGSPATIAL</b>), 2026.</font> 141 <br> 142 <a href="#" target="_blank"><font color="#2D61FF">paper</font></a> 143 <br> 144 </p> 145 </td> 146 </tr> 147 148 <tr> 149 <td><img src="./publication/ECCV-26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 150 <td valign=top> 151 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 152 <font style="font-weight:bold">Towards Long-Form Spatio-Temporal Video Grounding</font> 153 <br> 154 <font color="#000000">X. Gu, B. Fan, J. Yao, Z. Zhang, Y. Huang, C. Han, H. Fan†, and L. Zhang†</font> 155 <br> 156 <font>European Conference on Computer Vision (<b>ECCV</b>), 2026.</font> 157 <br> 158 <a href="https://arxiv.org/abs/2602.23294" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/HengLan/ART-STVG" target="_blank"><font color="#2D61FF">code</font></a> 159 <br> 160 </p> 161 </td> 162 </tr> 163 164 <tr> 165 <td><img src="./publication/iros-26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 166 <td valign=top> 167 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 168 <font style="font-weight:bold">Learning to Segment Liquids in Real-world Images</font> 169 <br> 170 <font color="#000000">J. Li, M. Li, L. Liu, X. Yuan, and H. Fan</font> 171 <br> 172 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2026.</font> 173 <br> 174 <a href="https://arxiv.org/abs/2601.00940" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/lonaslee/LQDM" target="_blank"><font color="#2D61FF">code</font></a> 175 <br> 176 </p> 177 </td> 178 </tr> 179 180 <tr> 181 <td><img src="./publication/ACLF-26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 182 <td valign=top> 183 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 184 <font style="font-weight:bold">ProMCP: Profiling Token Flows and Latency Costs in Model Context ProtocolâBased LLM Agents</font> 185 <br> 186 <font color="#000000">S. Anjum, W. Zheng, R. Kettimuthu, H. Fan, and Y. Feng</font> 187 <br> 188 <font>Findings of the Annual Meeting of the Association for Computational Linguistics (<b>ACL Findings</b>), 2026.</font> 189 <br> 190 <a href="https://openreview.net/attachment?id=ty6y1WiVzk&name=pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ResponsibleAILab/ProMCP" target="_blank"><font color="#2D61FF">code</font></a> 191 <br> 192 </p> 193 </td> 194 </tr> 195 196 <tr> 197 <td><img src="./publication/DMTrack.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 198 <td valign=top> 199 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 200 <font style="font-weight:bold">DMTrack: Spatio-Temporal Multimodal Tracking via Dual-Adapter</font> 201 <br> 202 <font color="#000000">W. Li, S. Dong, H. Lu, Y. Zhang, H. Fan†, and L. Zhang†</font> 203 <br> 204 <font>IEEE International Conference on Robotics and Automation (<b>ICRA</b>), 2026.</font> 205 <br> 206 <a href="https://arxiv.org/abs/2508.01592" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/Nightwatch-Fox11/DMTrack" target="_blank"><font color="#2D61FF">code</font></a> 207 <br> 208 </p> 209 </td> 210 </tr> 211 212 <tr> 213 <td><img src="./publication/OmniSTVG.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 214 <td valign=top> 215 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 216 <font style="font-weight:bold">OmniSTVG: Toward Spatio-Temporal Omni-Object Video Grounding</font> 217 <br> 218 <font color="#000000">J. Yao*, X. Gu*, X. Deng, M. Dai, B. Fan, Z. Zhang, Y. Huang, H. Fan†, and L. Zhang†</font> 219 <br> 220 <font>International Conference on Learning Representations (<b>ICLR</b>), 2026.</font> 221 <br> 222 <a href="https://arxiv.org/abs/2503.10500" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/JellyYao3000/OmniSTVG" target="_blank"><font color="#2D61FF">code-data</font></a> 223 <br> 224 </p> 225 </td> 226 </tr> 227 228 <tr> 229 <td><img src="./publication/IRDFusion.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 230 <td valign=top> 231 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 232 <font style="font-weight:bold">IRDFusion: Iterative Relation-Map Difference guided Feature Fusion for Multispectral Object Detection</font> 233 <br> 234 <font color="#000000">J. Shen, H. Zhan, X. Zuo, H. Fan, X. Yuan, J. Li, and W. Yang</font> 235 <br> 236 <font>Pattern Recognition (<b>PR</b>), 176: 113189, 2026.</font> 237 <br> 238 <a href="https://arxiv.org/abs/2509.09085" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/61s61min/IRDFusion" target="_blank"><font color="#2D61FF">code</font></a> 239 <br> 240 </p> 241 </td> 242 </tr> 243 244 <tr> 245 <td><img src="./publication/EACL26-findings.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 246 <td valign=top> 247 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 248 <font style="font-weight:bold">Harmful Factuality: LLMs Correcting What They Shouldn't</font> 249 <br> 250 <font color="#000000">M. Li, H. Zhang, H. Fan, J. Ding, and Y. Feng</font> 251 <br> 252 <font>Findings of the European Chapter of the Association for Computational Linguistics (<b>EACL Findings</b>), 2026.</font> 253 <br> 254 <a href="https://openreview.net/pdf?id=T9ot1VVtUb" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ResponsibleAILab/Harmful-Factuality-Hallucination" target="_blank"><font color="#2D61FF">code</font></a> 255 <br> 256 </p> 257 </td> 258 </tr> 259 260 <tr> 261 <td><img src="./publication/wacv-26.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 262 <td valign=top> 263 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 264 <font style="font-weight:bold">Structured Context Learning for Generic Event Boundary Detection</font> 265 <br> 266 <font color="#000000">X. Gu*, C. Li*, X. Wang, D. Hong, L. Zhang, T. Luo, L. Wen, and H. Fan</font> 267 <br> 268 <font>IEEE/CVF Winter Conference on Applications of Computer Vision (<b>WACV</b>), 2026.</font> 269 <br> 270 <a href="https://arxiv.org/abs/2512.00475" target="_blank"><font color="#2D61FF">paper</font></a> 271 <br> 272 </p> 273 </td> 274 </tr> 275 276 </table> 277 278 <HR> 279 280 <font size="4" color="black"><b>2025</b></font> 281 <br> 282 283 <table border=0 cellpadding=4> 284 285 <tr> 286 <td><img src="./publication/planartrack_ext.gif", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 287 <td valign=top> 288 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 289 <font style="font-weight:bold">PlanarTrack: A High-quality and Challenging Benchmark for Large-scale Planar Object Tracking</font> 290 <br> 291 <font color="#000000">Y. Jiao, X. Liu, X. Liu, X. Yuan, H. Fan, and L. Zhang</font> 292 <br> 293 <font>Computer Vision and Image Understanding (<b>CVIU</b>), 306: 130848, 2025.</font> 294 <br> 295 <a href="https://arxiv.org/abs/2510.23368" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://huggingface.co/datasets/Ailovejinx/planartrackplus" target="_blank"><font color="#2D61FF">data</font></a> 296 <br> 297 </p> 298 </td> 299 </tr> 300 301 <tr> 302 <td><img src="./publication/LMEEC.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 303 <td valign=top> 304 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 305 <font style="font-weight:bold">Robust Ego-Exo Correspondence with Long-Term Memory</font> 306 <br> 307 <font color="#000000">Y. Hu*, B. Fan*, X. Gu, H. Ren, D. Liu, H. Fan†, and L. Zhang†</font> 308 <br> 309 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2025.</font> 310 <br> 311 <a href="https://arxiv.org/abs/2510.11417" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/juneyeeHu/LM-EEC" target="_blank"><font color="#2D61FF">code</font></a> 312 <br> 313 </p> 314 </td> 315 </tr> 316 317 <tr> 318 <td><img src="./publication/loratv2.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 319 <td valign=top> 320 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 321 <font style="font-weight:bold">LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers</font> 322 <br> 323 <font color="#000000">L. Lin, H. Fan, Z. Zhang, Y. Huang, Y. Wang, Y. Xu, and H. Ling</font> 324 <br> 325 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2025. (<b>Spotlight</b>)</font> 326 <br> 327 <a href="https://openreview.net/pdf?id=q06YjUj0FB" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/LitingLin/LoRATv2" target="_blank"><font color="#2D61FF">code</font></a> 328 <br> 329 </p> 330 </td> 331 </tr> 332 333 <tr> 334 <td><img src="./publication/CaPT.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 335 <td valign=top> 336 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 337 <font style="font-weight:bold">All You Need is One: Capsule Prompt Tuning with a Single Vector</font> 338 <br> 339 <font color="#000000">Y. Liu, J. Liang, H. Fan, W. Yang, Y. Cui, X. Han, L. Huang, D. Liu, Q. Wang, and C. Han</font> 340 <br> 341 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2025.</font> 342 <br> 343 <a href="https://arxiv.org/abs/2510.16670" target="_blank"><font color="#2D61FF">paper</font></a> 344 <br> 345 </p> 346 </td> 347 </tr> 348 349 <tr> 350 <t
350d><img src="./publication/DPGTR.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 351 <td valign=top> 352 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 353 <font style="font-weight:bold">DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting</font> 354 <br> 355 <font color="#000000">M. Li, H. Fan, S. Fu, J. Ding, and Y. Feng</font> 356 <br> 357 <font>Findings of the Conference on Empirical Methods in Natural Language Processing (<b>EMNLP Findings</b>), 2025.</font> 358 <br> 359 <a href="https://arxiv.org/abs/2503.04990" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/FatShion-FTD/DP-GTR" target="_blank"><font color="#2D61FF">code</font></a> 360 <br> 361 </p> 362 </td> 363 </tr> 364 365 <tr> 366 <td><img src="./publication/ICCV-25-PRVQL.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 367 <td valign=top> 368 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 369 <font style="font-weight:bold">PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization</font> 370 <br> 371 <font color="#000000">B. Fan, Y. Feng, Y. Tian, J. Liang, Y. Lin, Y. Huang, and H. Fan</font> 372 <br> 373 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2025.</font> 374 <br> 375 <a href="https://arxiv.org/abs/2502.07707" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/fb-reps/PRVQL" target="_blank"><font color="#2D61FF">code</font></a> 376 <br> 377 </p> 378 </td> 379 </tr> 380 381 <tr> 382 <td><img src="./publication/ICCV-25-GSOT3D.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 383 <td valign=top> 384 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 385 <font style="font-weight:bold">GSOT3D: Towards Generic 3D Single Object Tracking in the Wild</font> 386 <br> 387 <font color="#000000">Y. Jiao*, Y. Li*, J. Ding, Q. Yang, S. Fu, H. Fan†, and L. Zhang†</font> 388 <br> 389 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2025.</font> 390 <br> 391 <a href="https://arxiv.org/abs/2412.02129" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ailovejinx/GSOT3D" target="_blank"><font color="#2D61FF">code-data</font></a> 392 <br> 393 </p> 394 </td> 395 </tr> 396 397 <tr> 398 <td><img src="./publication/ICCV-25-OV-MOT.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 399 <td valign=top> 400 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 401 <font style="font-weight:bold">Attention to Trajectory: Trajectory-Aware Open-Vocabulary Tracking</font> 402 <br> 403 <font color="#000000">Y. Li*, Y. Jiao*, D. Meng, H. Fan†, and L. Zhang†</font> 404 <br> 405 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2025.</font> 406 <br> 407 <a href="https://arxiv.org/abs/2503.08145" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/Nathan-Li123/TRACT" target="_blank"><font color="#2D61FF">code</font></a> 408 <br> 409 </p> 410 </td> 411 </tr> 412 413 <tr> 414 <td><img src="./publication/MICCAI-25-HRViT.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 415 <td valign=top> 416 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 417 <font style="font-weight:bold">Edge-Aware Token Halting for Efficient and Accurate Medical Image Segmentation</font> 418 <br> 419 <font color="#000000">Y. Guo, B. Song, H. Fan, and E. Cheng</font> 420 <br> 421 <font>International Conference on Medical Image Computing and Computer Assisted Intervention (<b>MICCAI</b>), 2025.</font> 422 <br> 423 <a href="./publication/MICCAI-25-HRViT.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/guoyh6/hrvit" target="_blank"><font color="#2D61FF">code</font></a> 424 <br> 425 </p> 426 </td> 427 </tr> 428 429 <tr> 430 <td><img src="./publication/IROS-25-tracking.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 431 <td valign=top> 432 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 433 <font style="font-weight:bold">Efficient and Accurate Low-Resolution Transformer Tracking</font> 434 <br> 435 <font color="#000000">S. Dong, Y. Feng, J. Liang, Q. Yang, Y. Lin, and H. Fan</font> 436 <br> 437 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2025. (<b>Oral</b>)</font> 438 <br> 439 <a href="https://arxiv.org/abs/2405.17660" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ShaohuaDong2021/LoReTrack" target="_blank"><font color="#2D61FF">code</font></a> 440 <br> 441 </p> 442 </td> 443 </tr> 444 445 <tr> 446 <td><img src="./publication/IROS-25-action-recognition.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 447 <td valign=top> 448 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 449 <font style="font-weight:bold">G3CN: Gaussian Topology Refinement Gated Graph Convolutional Network for Skeleton-Based A
449ction Recognition</font> 450 <br> 451 <font color="#000000">H. Ren, Z. Luo, H. Fan, X. Yuan, G. Wang, and L. Zhang</font> 452 <br> 453 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2025. (<b>Oral</b>)</font> 454 <br> 455 <a href="https://arxiv.org/abs/2509.07335" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/CyanSea123/G3CN-Gaussian-Topology" target="_blank"><font color="#2D61FF">code</font></a> 456 <br> 457 </p> 458 </td> 459 </tr> 460 461 <tr> 462 <td><img src="./publication/inpainting-IJCV.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 463 <td valign=top> 464 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 465 <font style="font-weight:bold">High-Fidelity Image Inpainting with Multimodal Guided GAN Inversion</font> 466 <br> 467 <font color="#000000">L. Zhang*, Y. Yu*, J. Yao, and H. Fan</font> 468 <br> 469 <font>International Journal of Computer Vision (<b>IJCV</b>), 133: 5788-5805, 2025.</font> 470 <br> 471 <a href="https://arxiv.org/abs/2504.12844" target="_blank"><font color="#2D61FF">paper</font></a> 472 <br> 473 </p> 474 </td> 475 </tr> 476 477 <tr> 478 <td><img src="./publication/DAM.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 479 <td valign=top> 480 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 481 <font style="font-weight:bold">DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration</font> 482 <br> 483 <font color="#000000">H. Zhang, H. Fan, K. Sha, Y. Huang, and Y. Feng</font> 484 <br> 485 <font>Findings of the Annual Meeting of the Association for Computational Linguistics (<b>ACL Findings</b>), 2025.</font> 486 <br> 487 <a href="https://arxiv.org/abs/2506.11104" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ResponsibleAILab/DAM" target="_blank"><font color="#2D61FF">code</font></a> 488 <br> 489 </p> 490 </td> 491 </tr> 492 493 <tr> 494 <td><img src="./publication/cvpr25.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 495 <td valign=top> 496 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 497 <font style="font-weight:bold">CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes</font> 498 <br> 499 <font color="#000000">Z. Xue, M. Guo, H. Fan, S. Zhang, and Z. Zhang</font> 500 <br> 501 <font>IEEE/CVF Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2025.</font> 502 <br> 503 <a href="https://openaccess.thecvf.com/content/CVPR2025/html/Xue_CorrBEV_Multi-View_3D_Object_Detection_by_Correlation_Learning_with_Multi-modal_CVPR_2025_paper.html" target="_blank"><font><font color="#2D61FF">paper</font></font></a> 504 <br> 505 </p> 506 </td> 507 </tr> 508 509 <tr> 510 <td><img src="./publication/lamot.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 511 <td valign=top> 512 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 513 <font style="font-weight:bold">LaMOT: Language-Guided Multi-Object Tracking</font> 514 <br> 515 <font color="#000000">Y. Li*, X. Liu*, L. Liu, H. Fan†, and L. Zhang†</font> 516 <br> 517 <font>IEEE International Conference on Robotics and Automation (<b>ICRA</b>), 2025.</font> 518 <br> 519 <a href="https://arxiv.org/abs/2406.08324" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/Nathan-Li123/LaMOT" target="_blank"><font color="#2D61FF">code</font></a> 520 <br> 521 </p> 522 </td> 523 </tr> 524 525 <tr> 526 <td><img src="./publication/cgtrack.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 527 <td valign=top> 528 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 529 <font style="font-weight:bold">CGTrack: Cascade Gating Network with Hierarchical Feature Aggregation for UAV Tracking</font> 530 <br> 531 <font color="#000000">W. Li, X. Liu, H. Fan†, and L. Zhang†</font> 532 <br> 533 <font>IEEE International Conference on Robotics and Automation (<b>ICRA</b>), 2025.</font> 534 <br> 535 <a href="./publication/ICRA_2025_CGTrack.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/Nightwatch-Fox11/CGTrack" target="_blank"><font color="#2D61FF">code</font></a> 536 <br> 537 </p> 538 </td> 539 </tr> 540 541 <tr> 542 <td><img src="./publication/semo.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 543 <td valign=top> 544 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 545 <font style="font-weight:bold">The Devil is in the Quality: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection</font> 546 <br> 547 <font color="#000000" >Z. Zhang, Z. Li, H. Wang, H. Yuan, K. Wang, and H. Fan</font> 548 <br> 549 <font>IEEE International Conference on Robotics and Automation (<b>ICRA</b>), 2025.</font> 550 <br> 551 <a href="./publication/icra25-3d-detectopn.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 552 <br> 553 </p> 554 </td> 555 </tr> 556 557 <tr> 558 <td><img src="./publication/tastvg.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 559 <td valign=top> 560 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 561 <font style="font-weight:bold">Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding</font> 562 <br> 563 <font color="#000000" >X. Gu, Y. Shen, C. Luo, T. Luo, Y. Huang, Y. Lin, H. Fan†, L. Zhang†</font> 564 <br> 565 <font>International Conference on Learning Representations (<b>ICLR</b>), 2025. (<b>Oral</b>)</font> 566 <br> 567 <a href="https://arxiv.org/abs/2502.11168" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/TA-STVG-ICLR2025-slide.pdf" target="_blank"><font color="#2D61FF">slide</font></a> <a href="./publication/TASTVG-ICLR25-poster.pptx" target="_blank"><font color="#2D61FF">poster</font></a> <a href="https://github.com/HengLan/TA-STVG" target="_blank"><font color="#2D61FF">code</font></a> 568 <br> 569 </p> 570 </td> 571 </tr> 572 573 <tr> 574 <td><img src="./publication/attmot.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 575 <td valign=top> 576 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 577 <font style="font-weight:bold">AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes</font> 578 <br> 579 <font color="#000000" >Y. Li, Z. Xiao, L. Yang, D. Meng, X. Zhou, H. Fan, and L. Zhang</font> 580 <br> 581 <font>IEEE Transactions on Neural Networks and Learning Systems (<b>T-NNLS</b>), 36(3): 5454-5468, 2025. </font> 582 <br> 583 <a href="https://arxiv.org/abs/2308.07537" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/HengLan/AttMOT" target="_blank"><font color="#2D61FF">code</font></a> 584 <br> 585 </p> 586 </td> 587 </tr> 588 589 </table> 590 591 592 <HR> 593 <font size="4" color="black"><b>2024</b></font> 594 <br> 595 596 <table border=0 cellpadding=4> 597 598 <tr> 599 <td><img src="./publication/vasttrack.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 600 <td valign=top> 601 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 602 <font style="font-weight:bold">VastTrack: Vast Category Visual Object Tracking</font> 603 <br> 604 <font color="#000000" >L. Peng*, J. Gao*, X. Liu*, W. Li*, S. Dong*, Z. Zhang, H. Fan†, and L. Zhang†</font> 605 <br> 606 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2024.</font> 607 <br> 608 <a href="https://arxiv.org/abs/2403.03493" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/VastTrack-poster.pdf" target="_blank"><font color="#2D61FF">poster</font></a> <a href="https://github.com/HengLan/VastTrack" target="_blank"><font color="#2D61FF">code-benchmark</font></a> 609 <br> 610 </p> 611 </td> 612 </tr> 613 614 <tr> 615 <td><img src="./publication/transflow.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 616 <td valign=top> 617 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 618 <font style="font-weight:bold">Optical Flow as Spatial-Temporal Attention Learners</font> 619 <br> 620 <font color="#000000" >Y. Lu, C. Han, Q. Wang, H. Fan, Z. Kong, D. Liu, and Y. Chen</font> 621 <br> 622 <font>IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>PAMI</b>), 46(12): 11491-11506, 2024. </font> 623 <br> 624 <a href="./publication/PAMI_TransFlow.pdf" target="_blank"><font><font color="#2D61FF">paper</font></font></a> 625 <br> 626 </p> 627 </td> 628 </tr> 629 630 <tr> 631 <td><img src="./publication/cyclicrefiner.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 632 <td valign=top> 633 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 634 <font style="font-weight:bold">Cyclic Refiner: Object-Aware Temporal Representation Learning for Multi-View 3D Detection and Tracking</font> 635 <br> 636 <font color="#000000" >M. Guo, Z. Zhang, L. Jing, Y. He, K. Wang, and H. Fan</font> 637 <br> 638 <font>International Journal of Computer Vision (<b>IJCV</b>), 132: 6184â6206, 2024.</font> 639 <br> 640 <a href="./publication/CyclicRefiner.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 641 <br> 642 </p> 643 </td> 644 </tr> 645 646 <tr> 647 <td><img src="./publication/smotsmall.gif", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 648 <td valign=top> 649 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 650 <font style="font-weight:bold">Beyond MOT: Semantic Multi-Object Tracking</font> 651 <br> 652 <font color="#000000" >Y. Li, Q. Li, H. Wang, X. Ma, J. Yao, S. Dong, H. Fan†, and L. Zhang† </font> 653 <br> 654 <font>European Conference on Computer Vision (<b>ECCV</b>), 2024.</font> 655 <br> 656 <a href="https://arxiv.org/abs/2403.05021" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/HengLan/SMOT" target="_blank"><font color="#2D61FF">code-data</font></a> 657 <br> 658 </p> 659 </td> 660 </tr> 661 662 <tr> 663 <td><img src="./publication/lorat.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 664 <td valign=top> 665 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 666 <font style="font-weight:bold">Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance</font> 667 <br> 668 <font color="#000000" >L. Lin, H. Fan, Z. Zhang, Y. Wang, Y. Xu, and H. Ling</font> 669 <br> 670 <font>European Conference on Computer Vision (<b>ECCV</b>), 2024.</font> 671 <br> 672 <a href="https://arxiv.org/abs/2403.05231" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/LitingLin/LoRAT" target="_blank"><font color="#2D61FF">code</font></a> 673 <br> 674 </p> 675 </td> 676 </tr> 677 678 <tr> 679 <td><img src="./publication/dplnet.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 680 <td valign=top> 681 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 682 <font style="font-weight:bold">Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning</font> 683 <br> 684 <font color="#000000" >S. Dong, Y. Feng, Q. Yang, Y. Huang, D. Liu, and H. Fan</font> 685 <br> 686 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2024. (<b>Oral</b>)</font> 687 <br> 688 <a href="https://arxiv.org/abs/2312.00360" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/ShaohuaDong2021/DPLNet" target="_blank"><font color="#2D61FF">code</font></a> 689 <br> 690 </p> 691 </td> 692 </tr> 693 694 <tr> 695 <td><img src="./publication/sicp.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 696 <td valign=top> 697 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 698 <font style="font-weight:bold">SiCP: Simultaneous Individual and Cooperative Perception for 3D Object Detection in Connected and Automated Vehicles</font> 699 <br> 700 <font color="#000000" >D. Qu, Q. Chen, T. Bai, A. Qin, H. Lu, H. Fan, S. Fu, and Q. Yang</font> 701 <br> 702 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2024. (<b>Oral</b>)</font> 703 <br> 704 <a href="https://arxiv.org/abs/2312.04822" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/DarrenQu/SiCP" target="_blank"><font color="#2D61FF">code</font></a> 705 <br> 706 </p> 707 </td> 708 </tr> 709 710 <td><img src="./publication/mga.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 711 <td valign=top> 712 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 713 <font style="font-weight:bold">Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment</font> 714 <br> 715 <font color="#000000" >L. Zhang, W. Zhou, H. Fan‡, T. Luo, and H. Ling (‡<b>corresponding author</b>)</font> 716 <br> 717 <font>IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>PAMI</b>), 46(12): 9161-9178, 2024. </font> 718 <br> 719 <a href="https://arxiv.org/abs/2301.00371" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/tiankongzhang/MGA" target="_blank"><font color="#2D61FF">code</font></a> 720 <br> 721 </p> 722 </td> 723 724 <tr> 725 <td><img src="./publication/vlt23.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 726 <td valign=top> 727 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 728 <font style="font-weight:bold">Divert More Attention to Vision-Language Object Tracking</font> 729 <br> 730 <font color="#000000" >M. Guo, Z. Zhang, L. Jing, H. Ling, and H. Fan</font> 731 <br> 732 <font>IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>PAMI</b>), 46(12): 8600-8618, 2024. </font> 733 <br> 734 <a href="https://arxiv.org/abs/2307.10046" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/JudasDie/SOTS" target="_blank"><font color="#2D61FF">code</font></a> 735 <br> 736 </p> 737 </td> 738 </tr> 739 740 <tr> 741 <td><img src="./publication/cgstvg.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 742 <td valign=top> 743 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 744 <font style="font-weight:bold">Context-Guided Spatio-Temporal Video Grounding</font> 745 <br> 746 <font color="#000000">X. Gu*, H. Fan*, Y. Huang, T. Luo, and L. Zhang</font> 747 <br> 748 <font>IEEE/CVF Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2024. </font> 749 <br> 750 <a href="https://arxiv.org/abs/2401.01578" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/CG-STVG-CVPR24-poster.pdf" target="_blank"><font color="#2D61FF">poster</font></a> <a href="https://github.com/HengLan/CGSTVG" target="_blank"><font color="#2D61FF">code</font></a> 751 <br> 752 </p> 753 </td> 754 </tr> 755 756 <tr> 757 <td><img src="./publication/motionlearner2.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 758 <td valign=top> 759 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 760 <font style="font-weight:bold">ProMotion: Prototyp
760es As Motion Learners</font> 761 <br> 762 <font color="#000000">Y. Lu, D. Liu, Q. Wang, C. Han, Y. Cui, Z. Cao, X. Zhang, Y. Chen, and H. Fan</font> 763 <br> 764 <font>IEEE/CVF Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2024 </font> 765 <br> 766 <a href="https://arxiv.org/abs/2406.04999" target="_blank"><font color="#2D61FF">paper</font></a> 767 <br> 768 </p> 769 </td> 770 </tr> 771 772 <tr> 773 <td><img src="./publication/textdet.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 774 <td valign=top> 775 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 776 <font style="font-weight:bold">Kernel Adaptive Convolution for Scene Text Detection via Distance Map Prediction</font> 777 <br> 778 <font color="#000000">J. Zheng, H. Fan, and L. Zhang</font> 779 <br> 780 <font>IEEE/CVF Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2024 </font> 781 <br> 782 <a href="./publication/Text_detection_CVPR_2024_paper.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 783 <br> 784 </p> 785 </td> 786 </tr> 787 788 789 <tr> 790 <td><img src="./publication/magic.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 791 <td valign=top> 792 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 793 <font style="font-weight:bold">MaGIC: Multi-modality Guided Image Completion</font> 794 <br> 795 <font color="#000000">H. Wang*, Y. Yu*, T. Luo, H. Fan, and L. Zhang</font> 796 <br> 797 <font>International Conference on Learning Representations (<b>ICLR</b>), 2024. </font> 798 <br> 799 <a href="https://arxiv.org/abs/2305.11818" target="_blank"><font color="#2D61FF">paper</font></a> <a href="http://www.yongshengyu.com/MaGIC-Page/" target="_blank"><font color="#2D61FF">project</font></a> <a href="https://github.com/yeates/MaGIC" target="_blank"><font color="#2D61FF">code</font></a> 800 <br> 801 </p> 802 </td> 803 </tr> 804 805 <tr> 806 <td><img src="./publication/gebd.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 807 <td valign=top> 808 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 809 <font style="font-weight:bold">Local Compressed Video Stream Learning for Generic Event Boundary Detection</font> 810 <br> 811 <font color="#000000" >L. Zhang, X. Gu, C. Li, T. Luo, and H. Fan</font> 812 <br> 813 <font>International Journal of Computer Vision (<b>IJCV</b>), 132: 1187-1204, 2024. </font> 814 <br> 815 <a href="https://arxiv.org/abs/2309.15431" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/GX77/LCVSL" target="_blank"><font color="#2D61FF">code</font></a> 816 <br> 817 </p> 818 </td> 819 </tr> 820 821 <tr> 822 <td><img src="./publication/sspnet.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 823 <td valign=top> 824 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 825 <font style="font-weight:bold">SSPNet: Scale and Spatial Priors Guided Generalizable and Interpretable Pedestrian Attribute Recognition</font> 826 <br> 827 <font color="#000000">J. Shen, T. Guo, X. Zuo, H. Fan, and W. Yang</font> 828 <br> 829 <font>Pattern Recognition (<b>PR</b>), 148: 110194, 2024. </font> 830 <br> 831 <a href="https://arxiv.org/abs/2312.06049" target="_blank"><font color="#2D61FF">paper</font></a> 832 <br> 833 </p> 834 </td> 835 </tr> 836 837 <tr> 838 <td><img src="./publication/ica.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 839 <td valign=top> 840 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 841 <font style="font-weight:bold">ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detection</font> 842 <br> 843 <font color="#000000">J. Shen, Y. Chen, Y. Liu, X. Zuo, H. Fan, and W. Yang</font> 844 <br> 845 <font>Pattern Recognition (<b>PR</b>), 145: 109913, 2024. </font> 846 <br> 847 <a href="https://arxiv.org/abs/2308.07504" target="_blank"><font color="#2D61FF">paper</font></a>
847 <a href="https://github.com/chanchanchan97/ICAFusion" target="_blank"><font color="#2D61FF">code</font></a> 848 <br> 849 </p> 850 </td> 851 </tr> 852 853 854 </table> 855 856 857 <HR> 858 <font size="4" color="black"><b>2023</b></font> 859 <br> 860 861 <table border=0 cellpadding=4> 862 863 <tr> 864 <td><img src="./publication/sigspatial-23.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 865 <td valign=top> 866 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 867 <font style="font-weight:bold">A Multi-granularity Decade-Long Geo-Tagged Twitter Dataset for Spatial Computing</font> 868 <br> 869 <font color="#000000" >Y. Feng, Z. Meng, C. Clemmer, H. Fan, and Y. Huang</font> 870 <br> 871 <font>ACM International Conference on Advances in Geographic Information Systems (<b>SIGSPATIAL</b>), 2023. </font> 872 <br> 873 <a href="./publication/SIGSPATIAL-2023.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://sigspatial.yunhefeng.me/" target="_blank"><font color="#2D61FF">project-data</font></a> 874 <br> 875 </p> 876 </td> 877 </tr> 878 879 <tr> 880 <td><img src="./publication/pid.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 881 <td valign=top> 882 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 883 <font style="font-weight:bold">PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection</font> 884 <br> 885 <font color="#000000" >L. Zhang, L. Jiang, R. Ji, and H. Fan</font> 886 <br> 887 <font>International Journal of Computer Vision (<b>IJCV</b>), 131: 3170-3192, 2023. </font> 888 <br> 889 <a href="https://arxiv.org/abs/2211.10763" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/lutao2021/PIDray" target="_blank"><font color="#2D61FF">code-data</font></a> 890 <br> 891 </p> 892 </td> 893 </tr> 894 895 <tr> 896 <td><img src="./publication/cviu-23.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 897 <td valign=top> 898 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 899 <font style="font-weight:bold">Collaborative Three-Stream Transformers for Video Captioning</font> 900 <br> 901 <font color="#000000" >H. Wang, L. Zhang, H. Fan, and T. Luo</font> 902 <br> 903 <font>Computer Vision and Image Understanding (<b>CVIU</b>), 235: 103799, 2023.</font> 904 <br> 905 <a href="./publication/CVIU-COST-23.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/wanghao14/COST" target="_blank"><font color="#2D61FF">code</font></a> 906 <br> 907 </p> 908 909 </td> 910 </tr> 911 912 <tr> 913 <td><img src="./publication/nsa.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 914 <td valign=top> 915 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 916 <font style="font-weight:bold">Unsupervised Domain Adaptive Detection with Network Stability Analysis</font> 917 <br> 918 <font color="#000000" >W. Zhou*, H. Fan*, T. Luo, and L. Zhang</font> 919 <br> 920 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2023.</font> 921 <br> 922 <a href="https://arxiv.org/pdf/2308.08182.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/tiankongzhang/NSA" target="_blank"><font color="#2D61FF">code</font></a> 923 <br> 924 </p> 925 </td> 926 </tr> 927 928 <tr> 929 <td><img src="./publication/unist.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 930 <td valign=top> 931 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 932 <font style="font-weight:bold"> Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers</font> 933 <br> 934 <font color="#000000" >B. Gu, H. Fan, and L. Zhang</font> 935 <br> 936 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2023.</font> 937 <br> 938 <a href="https://arxiv.org/abs/2304.11335" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/NevSNev/UniST" target="_blank"><font color="#2D61FF">code</font></a> 939 <br> 940 </p> 941 </td> 942 </tr> 943 944 <tr> 945 <td><img src="./publication/captioning-iccv-23.png", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 946 <td valign=top> 947 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 948 <font style="font-weight:bold">Accurate and Fast Compressed Video Captioning</font> 949 <br> 950 <font color="#000000" >Y. Shen, X. Gu, K. Xu, H. Fan, L. Wen, and L. Zhang</font> 951 <br> 952 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2023.</font> 953 <br> 954 <a href="https://arxiv.org/abs/2309.12867" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/acherstyx/CoCap" target="_blank"><font color="#2D61FF">code</font></a> 955 <br> 956 </p> 957 </td> 958 </tr> 959 960 <tr> 961 <td><img src="./publication/planartrack.gif", style="border-radius:5% 5% 5% 5%; border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 962 <td valign=top> 963 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 964 <font style="font-weight:bold">PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking</font> 965 <br> 966 <font color="#000000" >X. Liu*, X. Liu*, Z. Yi*, X. Zhou*, T. Le, L. Zhang, Y. Huang, Q. Yang, and H. Fan</font> 967 <br> 968 <font>IEEE/CVF International Conference on Computer Vision (<b>ICCV</b>), 2023.</font> 969 <br> 970 <a href="https://arxiv.org/abs/2303.07625" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://hengfan2010.github.io/projects/PlanarTrack/" target="_blank"><font color="#2D61FF">code-data</font></a> 971 <br> 972 </p> 973 </td> 974 </tr> 975 976 <tr> 977 <td><img src="./publication/animaltrack.gif", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 978 <td valign=top> 979 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 980 <font style="font-weight:bold">AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild</font> 981 <br> 982 <font color="#000000" >L. Zhang*, J. Gao*, Z. Xiao, and H. Fan</font> 983 <br> 984 <font>International Journal of Computer Vision (<b>IJCV</b>), 131: 496-513, 2023.</font> 985 <br> 986 <a href="https://arxiv.org/abs/2205.00158" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://hengfan2010.github.io/projects/AnimalTrack/" target="_blank"><font color="#2D61FF">project with data</font></a> 987 <br> 988 </p> 989 990 </td> 991 </tr> 992 993 <!-- 994 <tr> 995 <td><img src="./publication/vot.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 996 <td valign=top> 997 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 998 <font style="font-weight:bold">Visual Object Tracking: Progress, Challenge, and Future</font> 999 <br> 1000 <font color="#000000">L. Zhang and H. Fan</font> 1001 <br> 1002 <font>The Innovation, 4(2), 100402, 2023. (Invited)</font> 1003 <br> 1004 <a href="https://www.cell.com/the-innovation/fulltext/S2666-6758(23)00030-9" target="_blank"><font color="#2D61FF">paper</font></a> 1005 <br> 1006 </p> 1007 </td> 1008 </tr> 1009 --> 1010 1011 </table> 1012 1013 1014 1015 <HR> 1016 <font size="4" color="black"><b>2022</b></font> 1017 <br> 1018 1019 <table border=0 cellpadding=4> 1020 1021 1022 <tr> 1023 <td><img src="./publication/swintrack.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1024 <td valign=top> 1025 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1026 <font style="font-weight:bold">SwinTrack: A Simple and Strong Baseline for Transformer Tracking</font> 1027 <br> 1028 <font color="#000000" >L. Lin*, H. Fan*, Z. Zhang, Y. Xu, and H. Ling</font> 1029 <br> 1030 <font> Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2022.</font> 1031 <br> 1032 <a href="./publication/SwinTrack-NeurIPS-2022.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/swintrack-poster.pdf" target="_blank"><font color="#2D61FF">poster</font></a> <a href="https://github.com/HengLan/SwinTrack" target="_blank"><font color="#2D61FF">code</font></a> 1033 <br> 1034 </p> 1035 1036 </td> 1037 </tr> 1038 1039 <tr> 1040 <td><img src="./publication/vlt.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1041 <td valign=top> 1042 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1043 <font style="font-weight:bold">Divert More Attention to Vision-Language Tracking</font> 1044 <br> 1045 <font color="#000000" >M. Guo*, Z. Zhang*, H. Fan, and L. Jing</font> 1046 <br> 1047 <font>Advances in Neural Information Processing Systems (<b>NeurIPS</b>), 2022.</font> 1048 <br> 1049 <a href="./publication/VLT-NeurIPS-2022.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/vlt-poster.pdf" target="_blank"><font color="#2D61FF">poster</font></a> <a href="https://github.com/JudasDie/SOTS" target="_blank"><font color="#2D61FF">code</font></a> 1050 <br> 1051 </p> 1052 1053 </td> 1054 </tr> 1055 1056 <tr> 1057 <td><img src="./publication/invertfill.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1058 <td valign=top> 1059 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1060 <font style="font-weight:bold">High-Fidelity Image Inpainting with GAN Inversion</font> 1061 <br> 1062 <font color="#000000" >Y. Yu, L. Zhang, H. Fan, and T. Luo</font> 1063 <br> 1064 <font>European Conference on Computer Vision (<b>ECCV</b>), 2022.</font> 1065 <br> 1066 <a href="./publication/InvertFill-ECCV-2022.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="./publication/InvertFill-ECCV-2022-Supp.pdf" target="_blank"><font color="#2D61FF">supplementary</font></a> 1067 <br> 1068 </p> 1069 1070 </td> 1071 </tr> 1072 1073 <tr> 1074 <td><img src="./publication/media.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1075 <td valign=top> 1076 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1077 <font style="font-weight:bold">Towards Bridging the Distribution Gap: Instance to Prototype Earth Moverâs Distance for Distribution Alignment</font> 1078 <br> 1079 <font color="#000000" >Q. Zhou, R. Wang, G. Zeng, H. Fan, and G. Zheng</font> 1080 <br> 1081 <font>Medical Image Analysis (<b>MedIA</b>), 82: 102607, 2022.</font> 1082 <br>
1083 <a href="./publication/MedIA-2022.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1084 <br> 1085 </p> 1086 </td> 1087 </tr> 1088 1089 <tr> 1090 <td><img src="./publication/visdrone.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1091 <td valign=top> 1092 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1093 <font style="font-weight:bold">Detection and Tracking Meet Drones Challenge</font> 1094 <br> 1095 <font color="#000000" >P. Zhu, L. Wen, D. Du, X. Bian, H. Fan, Q. Hu, and H. Ling</font> 1096 <br> 1097 <font>IEEE Transactions on Pattern Analysis and Machine Intelligence (<b>PAMI</b>), 44(11): 7380-7399, 2022.</font> 1098 <br> 1099 <a href="https://arxiv.org/abs/2001.06303" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/VisDrone/VisDrone-Dataset" target="_blank"><font color="#2D61FF">code and project</font></a> 1100 <br> 1101 </p> 1102 </td> 1103 </tr> 1104 1105 <tr> 1106 <td><img src="./publication/glgan.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1107 <td valign=top> 1108 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1109 <font style="font-weight:bold">GL-GAN: Adaptive Global and Local Bilevel Optimization for Generative Adversarial Network</font> 1110 <br> 1111 <font color="#000000" >Y. Liu, H. Fan, X. Yuan, and J. Xiang</font> 1112 <br> 1113 <font>Pattern Recognition (<b>PR</b>), 123: 108375, 2022.</font> 1114 <br> 1115 <a href="publication\PR-22.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/summar6/GL-GAN" target="_blank"><font color="#2D61FF">code</font></a> 1116 <br> 1117 </p> 1118 </td> 1119 </tr> 1120 1121 <tr> 1122 <td><img src="./publication/inbn.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1123 <td valign=top> 1124 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1125 <font style="font-weight:bold">Learning Target-aware Representation for Visual Tracking via Informative Interactions</font> 1126 <br> 1127 <font color="#000000" >M. Guo, Z. Zhang, H. Fan, L. Jing, Y. Lyu, B. Li, and W. Hu</font> 1128 <br> 1129 <font>International Joint Conference on Artificial Intelligence (<b>IJCAI</b>), 2022. (<b>Long Oral</b>)</font> 1130 <br> 1131 <a href="https://arxiv.org/abs/2201.02526" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/JudasDie/SOTS" target="_blank"><font color="#2D61FF">code</font></a> 1132 <br> 1133 </p> 1134 1135 </td> 1136 </tr> 1137 1138 </table> 1139 1140 1141 <HR> 1142 <font size="4" color="black"><b>2021</b></font> 1143 <br> 1144 1145 <table border=0 cellpadding=4> 1146 1147 <tr> 1148 <td><img src="./publication/totb.gif", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1149 <td valign=top> 1150 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1151 <font style="font-weight:bold">Transparent Object Tracking Benchmark</font> 1152 <br> 1153 <font color="#000000">H. Fan, H. Miththanthaya, Harshit, S. Rajan, X. Liu, Z. Zou, Y. Lin, and H. Ling</font> 1154 <br> 1155 <font>IEEE International Conference on Computer Vision (<b>ICCV</b>), 2021.</font> 1156 <br> 1157 <a href="https://arxiv.org/abs/2011.10875" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://hengfan2010.github.io/projects/TOTB/" target="_blank"><font color="#2D61FF">code and project</font></a> 1158 <br> 1159 </p> 1160 1161 </td> 1162 </tr> 1163 1164 <tr> 1165 <td><img src="./publication/cract.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1166 <td valign=top> 1167 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1168 <font style="font-weight:bold">CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking</font> 1169 <br> 1170 <font color="#000000">H. Fan and H. Ling</font> 1171 <br> 1172 <font>IEEE/RSJ International Conference on Intelligent Robots and Systems (<b>IROS</b>), 2021.</font> 1173 <br> 1174 <a href="https://arxiv.org/abs/2011.12483" target="_blank"><font color="#2D61FF">paper</font></a> <a href="#" target="_blank"><font color="#2D61FF">project</font></a> 1175 <br> 1176 </p> 1177 </td> 1178 </tr> 1179 1180 <tr> 1181 <td><img src="./publication/lasotijcv.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1182 <td valign=top> 1183 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1184 <font style="font-weight:bold">LaSOT: A High-quality Large-scale Single Object Tracking Benchmark</font> 1185 <br> 1186 <font color="#000000" >H. Fan, H. Bai, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, Harshit, M. Huang, J. Liu, Y. Xu, C. Liao, L. Yuan, and H. Ling</font> 1187 <br> 1188 <font>International Journal of Computer Vision (<b>IJCV</b>), 129: 439-461, 2021.</font> 1189 <br> 1190 <a href="publication\IJCV-21.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="http://vision.cs.stonybrook.edu/~lasot/" target="_blank"><font color="#2D61FF">code and benchmark</font></a> 1191 <br> 1192 </p> 1193 </td> 1194 </tr> 1195 1196 <tr> 1197 <td><img src="./publication/clsgan.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1198 <td valign=top> 1199 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1200 <font style="font-weight:bold">ClsGAN: Selective Attribute Editing Based On Classification Adversarial Network</font> 1201 <br> 1202 <font color="#000000" >Y. Liu, H. Fan, F. Ni, and J. Xiang</font> 1203 <br> 1204 <font>Neural Networks (<b>NN</b>), 133: 220-228, 2021.</font> 1205 <br> 1206 <a href="publication\NN-2021.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://github.com/summar6/ClsGAN" target="_blank"><font color="#2D61FF">code</font></a> 1207 <br> 1208 </p> 1209 </td> 1210 </tr> 1211 1212 <tr> 1213 <td><img src="./publication/tracklinic.gif", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1214 <td valign=top> 1215 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1216 <font style="font-weight:bold">TracKlinic: Diagnosis of Challenge Factors in Visual Tracking</font> 1217 <br> 1218 <font color="#000000">H. Fan, F. Yang, P. Chu, Y. Lin, L. Yuan, and H. Ling</font> 1219 <br> 1220 <font>IEEE Winter Conference on Applications of Computer Vision (<b>WACV</b>), 2021.</font> 1221 <br> 1222 <a href="https://openaccess.thecvf.com/content/WACV2021/papers/Fan_TracKlinic_Diagnosis_of_Challenge_Factors_in_Visual_Tracking_WACV_2021_paper.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href=".\projects\TracKlinic\TracKlinic.htm" target="_blank"><font color="#2D61FF">project</font></a> 1223 <br> 1224 </p> 1225 </td> 1226 </tr> 1227 1228 <tr> 1229 <td><img src="./publication/mart.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1230 <td valign=top> 1231 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1232 <font style="font-weight:bold">MART: Motion-Aware Recurrent Neural Network for Robust Visual Tracking</font> 1233 <br> 1234 <font color="#000000">H. Fan and H. Ling</font> 1235 <br> 1236 <font>IEEE Winter Conference on Applications of Computer Vision (<b>WACV</b>), 2021.</font> 1237 <br> 1238 <a href="https://openaccess.thecvf.com/content/WACV2021/papers/Fan_MART_Motion-Aware_Recurrent_Neural_Network_for_Robust_Visual_Tracking_WACV_2021_paper.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="#" target="_blank"><font color="#2D61FF">project</font></a> 1239 <br> 1240 </p> 1241 </td> 1242 </tr> 1243 1244 <tr> 1245 <td><img src="./publication/regct.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1246 <td valign=top> 1247 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1248 <font style="font-weight:bold">Robust and Efficient Graph Correspondence Transfer for Person Re-identification</font> 1249 <br> 1250 <font color="#000000" >Q. Zhou, H. Fan, H. Yang, H. Su, S. Zheng, S. Wu, and H. Ling</font> 1251 <br> 1252 <font>IEEE Transactions on Image Processing (<b>T-IP</b>), 30: 1623-1638, 2021.</font> 1253 <br> 1254 <font><a href="publication\TIP-19-b.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://drive.google.com/file/d/1rt7DpXJIvRVCya463gt2jqxl71xy5o7J/view" target="_blank"><font color="#2D61FF">code</font></a></font> 1255 <br> 1256 </p> 1257 </td> 1258 </tr> 1259 1260 </table> 1261 1262 1263 1264 <HR> 1265 <font size="4" color="black"><b>2020</b></font> 1266 <br> 1267 1268 <table border=0 cellpadding=4> 1269 1270 <tr> 1271 <td><img src="./publication/wbc.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1272 <td valign=top> 1273 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1274 <font style="font-weight:bold">Weighted Bilinear Coding Over Salient Body Parts for Person Re-identification</font> 1275 <br> 1276 <font color="#000000" >Z. Chang, Q. Zhou, H. Fan, H. Yang, H. Su, S. Zheng, and H. Ling</font> 1277 <br> 1278 <font>Neurocomputing, 407: 454-464, 2020.</font> 1279 <br> 1280 <font><a href="publication\Neurocomputing-20.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1281 <br> 1282 </p> 1283 </td> 1284 </tr> 1285 1286 <tr> 1287 <td><img src="./publication/embc2020.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1288 <td valign=top> 1289 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1290 <font style="font-weight:bold">Detection of Trabecular Landmarks for Osteoporosis Prescreening in Dental Panoramic Radiogra
1290phs</font> 1291 <br> 1292 <font color="#000000">J. Ren, H. Fan, J. Yang, and H. Ling</font> 1293 <br> 1294 <font>IEEE Engineering in Medicine and Biology Society (<b>EMBC</b>), 2020.</font> 1295 <br> 1296 <a href="publication\EMBC-20.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1297 <br> 1298 </p> 1299 </td> 1300 </tr> 1301 1302 </table> 1303 1304 1305 <HR> 1306 <font size="4" color="black"><b>2019</b></font> 1307 <br> 1308 1309 <table border=0 cellpadding=4> 1310 1311 <tr> 1312 <td><img src="./publication/clusdet.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1313 <td valign=top> 1314 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1315 <font style="font-weight:bold">Clustered Object Detection in Aerial Images</font> 1316 <br> 1317 <font color="#000000" >F. Yang, H. Fan, P. Chu, E. Blasch, and H. Ling</font> 1318 <br> 1319 <font>IEEE International Conference on Computer Vision (<b>ICCV</b>), 2019.</font> 1320 <br> 1321 <a href="publication\ICCV-19.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://drive.google.com/file/d/1IrrU937Vdki4ibN6lAAi7FQ-yx4CWjJw/view" target="_blank"><font color="#2D61FF">supplementary</font></a> <a href="https://github.com/fyangneil/Clustered-Object-Detection-in-Aerial-Image" target="_blank"><font color="#2D61FF">code</font></a> 1322 <br> 1323 </p> 1324 </td> 1325 </tr> 1326 1327 <tr> 1328 <td><img src="./publication/st.gif", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1329 <td valign=top> 1330 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1331 <font style="font-weight:bold">Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking</font> 1332 <br> 1333 <font color="#000000" >H. Fan and H. Ling</font> 1334 <br> 1335 <font>IEEE Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2019.</font> 1336 <br> 1337 <a href="publication\CVPR-19-a.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://www3.cs.stonybrook.edu/~hling/code/CRPN/crpn.htm" target="_blank"><font color="#2D61FF">code</font></a> 1338 <br> 1339 </p> 1340 </td> 1341 </tr> 1342 1343 <tr> 1344 <td><img src="./publication/lasot.gif", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1345 <td valign=top> 1346 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1347 <font style="font-weight:bold">LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking</font> 1348 <br> 1349 <font color="#000000" >H. Fan, L. Lin, F. Yang, P. Chu, G. Deng, S. Yu, H. Bai, Y. Xu, C. Liao, and H. Ling</font> 1350 <br> 1351 <font>IEEE Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>), 2019.</font> 1352 <br> 1353 <a href="publication\CVPR-19-b.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="http://vision.cs.stonybrook.edu/~lasot/" target="_blank"><font color="#2D61FF">code and benchmark</font></a> 1354 <br> 1355 </p> 1356 </td> 1357 </tr> 1358 1359 <tr> 1360 <td><img src="./publication/wacv-19a-img.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1361 <td valign=top> 1362 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1363 <font style="font-weight:bold">Scene Parsing via Dense Recurrent Neural Networks with Attentional Selection</font> 1364 <br> 1365 <font color="#000000" >H. Fan, P. Chu, L. Latecki, and H. Ling</font> 1366 <br> 1367 <font>IEEE Winter Conference on Applications of Computer Vision (<b>WACV</b>), 2019.</font> 1368 <br> 1369 <a href="publication\WACV-19-a.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1370 <br> 1371 </p> 1372 </td> 1373 </tr> 1374 1375 <tr> 1376 <td><img src="./publication/wacv-19b-img.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1377 <td valign=top> 1378 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1379 <font style="font-weight:bold">Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment</font> 1380 <br> 1381 <font color="#000000" >P. Chu, H. Fan, C. Tan, and H. Ling</font> 1382 <br> 1383 <font>IEEE Winter Conference on Applications of Computer Vision (<b>WACV</b>), 2019.</font> 1384 <br> 1385 <a href="publication\WACV-19-b.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1386 <br> 1387 </p> 1388 </td> 1389 </tr> 1390 1391 <tr> 1392 <td><img src="./publication/ptavtip.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1393 <td valign=top> 1394 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1395 <font style="font-weight:bold">Parallel Tracking and Verifying</font> 1396 <br> 1397 <font color="#000000" >H. Fan and H. Ling</font> 1398 <br> 1399 <font>IEEE Transactions on Image Processing (<b>T-IP</b>), 28(8): 4130-4144, 2019.</font> 1400 <br> 1401 <font><a href="publication\TIP-19-a.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://www3.cs.stonybrook.edu/~hling/code/PTAV/ptav.htm" target="_blank"><font color="#2D61FF">code</font></a></font> 1402 <br> 1403 </p> 1404 </td> 1405 </tr> 1406 1407 </table> 1408 1409 1410 <HR> 1411 <font size="4" color="black"><b>2018</b></font> 1412 <br> 1413 1414 <table border=0 cellpadding=4> 1415 1416 <tr> 1417 <td><img src="./publication/mlrnns.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1418 <td valign=top> 1419 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1420 <font style="font-weight:bold">Multi-level Contextual RNNs with Attention Model for Scene Labeling</font> 1421 <br> 1422 <font color="#000000" >H. Fan, X. Mei, D. Prokhorov, and H. Ling</font> 1423 <br> 1424 <font>IEEE Transactions on Intelligent Transportation Systems (<b>T-ITS</b>), 19(11): 3475-3485, 2018.</font> 1425 <br> 1426 <font><a href="publication\TITS-18.pdf" target="_blank"><font color="#2D61FF">paper</font></a></font> 1427 <br> 1428 </p> 1429 </td> 1430 </tr> 1431 1432 <tr> 1433 <td><img src="./publication/gct.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1434 <td valign=top> 1435 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1436 <font style="font-weight:bold">Graph Correspondence Transfer for Person Re-identification</font> 1437 <br> 1438 <font color="#000000" >Q. Zhou, H. Fan, S. Zheng, H. Su, X. Li, S. Wu, and H. Ling</font> 1439 <br> 1440 <font>AAAI Conference on Artificial Intelligence (<b>AAAI</b>), 2018. (<b>Oral</b>)</font> 1441 <br> 1442 <a href="publication\AAAI-18.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="https://drive.google.com/file/d/1rt7DpXJIvRVCya463gt2jqxl71xy5o7J/view" target="_blank"><font color="#2D61FF">code</font></a> 1443 <br> 1444 </p> 1445 </td> 1446 </tr> 1447 1448 </table> 1449 1450 <HR> 1451 <font size="4" color="black"><b>2017</b></font> 1452 <br> 1453 1454 <table border=0 cellpadding=4> 1455 1456 <tr> 1457 <td><img src="./publication/ptaviccv.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1458 <td valign=top> 1459 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1460 <font style="font-weight:bold">Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking</font> 1461 <br> 1462 <font color="#000000" >H. Fan and H. Ling</font> 1463 <br> 1464 <font>IEEE International Conference on Computer Vision (<b>ICCV</b>), 2017.</font> 1465 <br> 1466 <a href="publication\ICCV-17.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="publication\ICCV17-poster.pdf" target="_blank"><font color="#2D61FF">poster</font></a> <a href="publication\ICCV17-slide.pdf" target="_blank"><font color="#2D61FF">slide</font></a> <a href="https://www3.cs.stonybrook.edu/~hling/code/PTAV/ptav.htm" target="_blank"><font color="#2D61FF">code</font></a> 1467 <br> 1468 </p> 1469 </td> 1470 </tr> 1471 1472 <tr> 1473 <td><img src="./publication/sanet.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1474 <td valign=top> 1475 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1476 <font style="font-weight:bold">SANet: Structure-Aware Network for Visual Tracking</font> 1477 <br> 1478 <font color="#000000" >H. Fan and H. Ling</font> 1479 <br> 1480 <font>IEEE Conference on Computer Vision and Pattern Recognition (<b>CVPR</b>) Workshop, 2017.</font> 1481 <br> 1482 <a href="publication\CVPRW-17.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="http://www.dabi.temple.edu/~hbling/code/SANet/SANet.html" target="_blank"><font color="#2D61FF">code</font></a> 1483 <br> 1484 </p> 1485 </td> 1486 </tr> 1487 1488 <tr> 1489 <td><img src="./publication/lgcf.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1490 <td valign=top> 1491 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1492 <font style="font-weight:bold">Robust Visual Tracking via Local-Global Correlation Filter</font> 1493 <br> 1494 <font color="#000000">H. Fan and J. Xiang</font> 1495 <br> 1496 <font>AAAI Conference on Artificial Intelligence (<b>AAAI</b>), 2017. (<b>Oral</b>)</font> 1497 <br> 1498 <a href="publication\AAAI-17.pdf" target="_blank"><font color="#2D61FF">paper</font></a> 1499 <br> 1500 </p> 1501 </td> 1502 </tr> 1503 1504 <tr> 1505 <td><img src="./publication/mjdl.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1506 <td valign=top> 1507 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1508 <font style="font-weight:bold">Robust Visual Tracking with Multitask Joint Dictionary Learning</font> 1509 <br> 1510 <font color="#000000" >H. Fan and J. Xiang</font> 1511 <br> 1512 <font>IEEE Transactions on Circuits and Systems for Video and Technology (<b>T-CSVT</b>), 27(5): 1018-1030, 2017.</font> 1513 <br> 1514 <font><a href="publication\TCSVT-17.pdf" target="_blank"><font color="#2D61FF">paper</font></a></font> <a href=".\projects\MJDL\MJDL.htm" target="_blank"><font color="#2D61FF">project</font></a> 1515 <br> 1516 </p> 1517 </td> 1518 </tr> 1519 1520 </table> 1521 1522 <HR> 1523 <font size="4" color="black"><b>2016</b></font> 1524 1525 1526 <table border=0 cellpadding=4> 1527 1528 <tr> 1529 <td><img src="./publication/iv.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=120 height="80"> </TD> 1530 <td valign=top> 1531 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1532 <font style="font-weight:bold">Cross Datasets Vegetation Detection with Spatial Prior and Local Context</font> 1533 <br> 1534 <font color="#000000" >H. Fan, X. Mei, D. Prokhorov, and H. Ling</font> 1535 <br> 1536 <font>IEEE Intelligent Vehicles Symposium (<b>IV</b>), 2016.</font> 1537 <br> 1538 <a href="publication\IV-16.pdf" target="_blank"><font color="#2D61FF">paper</font></a> <a href="#"><font color="#2D61FF">code and data (by request)</font></a> 1539 <br> 1540 </p> 1541 </td> 1542 </tr> 1543 1544 </table> 1545 1546 <HR> 1547 <font size="4" color="black"><b>PhD Dissertation</b></font> 1548 <br> 1549 1550 1551 <table border=0 cellpadding=4> 1552 1553 <tr> 1554 <td><img src="./publication/sbu.png", style="border-radius:5% 5% 5% 5%;border-color:#C8C4C3;" border="1" width=100> </TD> 1555 <td valign=top> 1556 <p style="line-height: 110%; margin-top: 5px; margin-bottom: 5px;"> 1557 <font style="font-weight:bold">Algorithms and Benchmarks for Robust Visual Object Tracking</font> 1558 <br> 1559 <font color="#000000" >H. Fan</font> 1560 <br> 1561 <font>Advisor: <a href="https://www3.cs.stonybrook.edu/~hling/" target="_blank"><font color="black">Prof. Haibin Ling</font></a></font> 1562 <br> 1563 <font>Committee: Professors <a href="https://www3.cs.stonybrook.edu/~gu/" target="_blank"><font color="black">Xianfeng Gu</font></a>, <a href="https://www3.cs.stonybrook.edu/~samaras/" target="_blank"><font color="black">Dimitris Samaras</font></a>, <a href="https://dentistry.temple.edu/about/faculty-staff/jie-yang-jiey
1563ang" target="_blank"><font color="black">Jie Yang</font></a></font> 1564 <br> 1565 <font>Department of Computer Science, State University of New York at Stony Brook, 2021.</font> 1566 <br> 1567 <a href="https://www.proquest.com/docview/2558097086?pq-origsite=gscholar&fromopenview=true" target="_blank"><font color="#2D61FF">pdf link</font></a> <a href="https://docs.google.com/presentation/d/1GsGYDb6WazjAaIxPu2P0QzxPfu4wp4Nn/edit?usp=share_link&ouid=116478199769662584478&rtpof=true&sd=true" target="_blank"><font color="#2D61FF">slide</font></a> 1568 <br> 1569 </p> 1570 </td> 1571 </tr> 1572 </table> 1573 1574 <HR> 1575 1576 Copyright Notice: The papers presented above are to ensure timely dissemination of scholarly and technical work and only for personal or classroom use. Copyright and all rights therein are retained by authors and/or by other copyright holders. 1577 1578 <HR> 1579</div> 1580 1581</div> 1582</body> 1583</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.